TTA-TTBA.md

Awesome Test-Time Instance Adaptation

A curated list of awesome test-time instance/ batch adaptation resources. Your contributions are always welcome!

Contents

• Test Time Instance Adaptation
• Test Time Batch Adaptation

Instance-level

Image classification

• GeOS [D'Innocente et al., arXiv 2019] Learning to generalize one sample at a time with self-supervision [PDF] [G-Scholar]

• TTT [Sun et al., Proc. ICML 2020] Test-time training with self-supervision for generalization under distribution shifts [PDF] [G-Scholar] [CODE-1] [CODE-2]

• PredBN [Nado et al., Proc. ICML Workshops 2020] Evaluating prediction-time batch normalization for robustness under covariate shift [PDF] [G-Scholar]

• PredBN+ [Schneider et al., Proc. NeurIPS 2020] Improving robustness against common corruptions by covariate shift adaptation [PDF] [G-Scholar] [CODE]

• DSON [Seo et al., Proc. ECCV 2020] Learning to optimize domain specific normalization for domain generalization [PDF] [G-Scholar]

• SSDN-TTT [Cohen et al., arXiv 2020] Self-supervised dynamic networks for covariate shift robustness [PDF] [G-Scholar]

• CNGRAD [Alet et al., Proc. NeurIPS 2021] Tailoring: Encoding inductive biases by optimizing unsupervised objectives at prediction time [PDF] [G-Scholar] [CODE--]

• ITTP [Pandey et al., Proc. CVPR 2021] Generalization on unseen domains via inference-time label-preserving target projections [PDF] [G-Scholar] [CODE]

• AugBN [Khurana et al., arXiv 2021] SITA: Single image test-time adaptation [PDF] [G-Scholar]

• SSGen [Xiao et al., Proc. ICLR 2022] Learning to generalize across domains on single test samples [PDF] [G-Scholar] [CODE]

• MEMO [Zhang et al., Proc. NeurIPS 2022] MEMO: Test time robustness via adaptation and augmentation [PDF] [G-Scholar] [CODE]

• TTT-MAE [Gandelsman et al., Proc. NeurIPS 2022] Test-time training with masked autoencoders [PDF] [G-Scholar] [CODE]

• DDG [Sun et al., Proc. IJCAI 2022] Dynamic domain generalization [PDF] [G-Scholar] [CODE]

• TAF-Cal [Zhao et al., Proc. IJCAI 2022] Test-time fourier style calibration for domain generalization [PDF] [G-Scholar] [CODE--]

• TTCP++ [Sarkar et al., Proc. WACV 2022] Leveraging test-time consensus prediction for robustness against unseen noise [PDF] [G-Scholar]

• MT3 [Bartler et al., Proc. AISTATS 2022] MT3: Meta test-time training for self-supervised test-time adaption [PDF] [G-Scholar] [CODE]

• TTAPS [Bartler et al., Proc. IJCNN 2022] TTAPS: Test-time adaption by aligning prototypes using self-supervision [PDF] [G-Scholar] [CODE]

• DoPrompt [Zheng et al., arXiv 2022] Prompt vision transformer for domain generalization [PDF] [G-Scholar] [CODE]

• DCN [Jiang et al., Proc. ECCV Workshops 2022] Domain-Conditioned normalization for test-time domain generalization [PDF] [G-Scholar]

• BNE [Segu et al., Pattern Recognition 2022] Batch normalization embeddings for deep domain generalization [PDF] [G-Scholar]

• GDU [Föll et al., arXiv 2022] Gated domain units for multi-source domain generalization [PDF] [G-Scholar] [CODE]

• TTN [Lim et al., Proc. ICLR 2023] TTN: A domain-shift aware batch normalization in test-time adaptation [PDF] [G-Scholar]

• ESA [Xiao et al., Proc. ICLR 2023] Energy-based test sample adaptation for domain generalization [PDF] [G-Scholar]

• TSB [Park et al., Proc. ICML 2023] Test-time style shifting: Handling arbitrary styles in domain generalization [PDF] [G-Scholar--]

  [Park et al., Proc. ICML Workshops 2022] Style balancing and test-time style shifting for domain generalization [PDF] [G-Scholar]

• PromptAlign [Samadh et al., Proc. NeurIPS 2023] Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization [PDF] [G-Scholar] [CODE]

• Diffusion-TTA [Prabhudesai et al., Proc. NeurIPS 2023] Test-time adaptation of discriminative models via diffusion generative feedback [PDF] [G-Scholar--] [CODE]

• DDA [Gao et al., Proc. CVPR 2023] Back to the source: Diffusion-driven adaptation to test-time corruption [PDF] [G-Scholar] [CODE]

  [Gao et al., Proc. Workshops 2023] Back to the source: Diffusion-driven test-time adaptation [PDF] [G-Scholar] [CODE]

• IAI [Jeon et al., Proc. ICCV 2023] A unified framework for robustness on diverse sampling errors [PDF] [G-Scholar]

• DRM [Zhang et al., Proc. KDD 2023] Domain-specific risk minimization for out-of-distribution generalization [PDF] [G-Scholar] [CODE]

• VPA [Sun et al., Proc. ACMMM 2023] VPA: Fully test-time visual prompt adaptation [PDF]) [G-Scholar]

• PE [Lin et al., Proc. ACMMM 2023] Parameter exchange for robust dynamic domain generalization [PDF]) [G-Scholar] [CODE]

• ... [Feng et al., Proc. ICASSP 2023] Test-time training-free domain adaptation [PDF] [G-Scholar--]

• TT-NSS [Mehra et al., Proc. ICML Workshops 2023] Risk-averse predictions on unseen domains via neural style smoothing [PDF] [G-Scholar--]

• ... [Taesiri et al., arXiv 2023] Zoom is what you need: An empirical study of the power of zoom and spatial biases in image classification [PDF] [G-Scholar]

• TTACIL [Marouf et al., arXiv 2023] Rethinking class-incremental learning in the era of large pre-trained models via test-time adaptation [PDF] [G-Scholar--] [CODE]

• TEA [Yuan et al., arXiv 2023] TEA: Test-time energy adaptation [PDF] [G-Scholar]

• GDDA [Song and Lai, arXiv 2023] Target to source: Guidance-based diffusion model for test-time adaptation [PDF] [G-Scholar]

• VDPG [Chi et al., Proc. ICLR 2024] Adapting to distribution shift by visual domain prompt generation [PDF] [G-Scholar--]

• GDA [Tsai et al., Proc. CVPR 2024] GDA: Generalized diffusion for robust test-time adaptation [PDF] [G-Scholar]

• MoDE [Ma et al., Proc. CVPR 2024] MoDE: CLIP data experts via clustering [PDF] [G-Scholar] [CODE]

• CloudFixer [Shim et al., Proc. ECCV 2024] CloudFixer: Test-time adaptation for 3D point clouds via diffusion-guided geometric transformation [PDF] [G-Scholar] [CODE]

• TPS [Sui et al., Proc. CVPR Workshops 2024] Just shift it: Test-time prototype shifting for zero-shot generalization with vision-language models [PDF] [G-Scholar] [CODE]

• ZERO [Farina et al., arXiv 2024] Frustratingly easy test-time adaptation of vision-language models [PDF] [G-Scholar] [CODE--]

• SDA [Guo et al., arXiv 2024] Everything to the synthetic: Diffusion-driven test-time adaptation via synthetic-domain alignment [PDF] [G-Scholar] [CODE]

• ... [Hu et al., arXiv 2024] Diffusion model driven test-time image adaptation for robust skin lesion classification [PDF] [G-Scholar] [CODE--]

• IT3 [Durasov et al., arXiv 2024] IT3: Idempotent test-time training [PDF] [G-Scholar--]

Segmentation

• DIEM [Wang et al., arXiv 2019] Dynamic scale inference by entropy minimization [PDF] [G-Scholar]

• SDA-Net [He et al., Proc. MICCAI 2020] Self domain adapted network [PDF] [G-Scholar] [CODE]

• TTA-DAE [Karani et al., Medical Image Analysis 2021] Test-time adaptable neural networks for robust medical image segmentation [PDF] [G-Scholar] [CODE]

• TTA-AE [He et al., Medical Image Analysis 2021] Autoencoder based self-supervised test-time adaptation for medical image analysis [PDF] [G-Scholar] [CODE]

• OST [Termöhlen, et al., Proc. ITSC 2021] Continual unsupervised domain adaptation for semantic segmentation by online frequency domain style transfer [PDF] [G-Scholar]

• CBNA [Klingner et al., IEEE TITS 2022] Continual batchnorm adaptation (CBNA) for semantic segmentation [PDF] [G-Scholar] [CODE]

• PSR [Li et al., Proc. MICCAI Workshops 2022] Plug-and-play shape refinement framework for multi-site and lifespan brain skull stripping [PDF] [G-Scholar]

• TTA-FoE [Karani et al., arXiv 2022] A field of experts prior for adapting neural networks at test time [PDF] [G-Scholar]

• AdvTTT [Valvano et al., Journal of Machine Learning for Biomedical Imaging 2022] Re-using adversarial mask discriminators for test-time training under distribution shifts [PDF] [G-Scholar] [CODE]

  [Valvano et al., Proc. MICCAI Workshops 2021] Stop throwing away discriminators! Re-using adversaries for test-time training [PDF] [G-Scholar]

• DCAC [Hu et al., IEEE TMI 2022] Domain and content adaptive convolution based multi-source domain generalization in medical image segmentation [PDF] [G-Scholar] [CODE]

• InstCal [Zou et al., Proc. ECCV 2022] Learning instance-specific adaptation for cross-domain segmentation [PDF] [G-Scholar] [CODE]

• TTO-AE [Li et al., Proc. MICCAI Workshops 2022] Self-supervised test-time adaptation for medical image segmentation [PDF] [G-Scholar] [CODE--]

• TASD [Liu et al., Proc. AAAI 2022] Single-domain generalization in medical image segmentation via test-time adaptation from shape dictionary [PDF] [G-Scholar]

• MALL [Reddy et al., Proc. ECCV 2022] Master of all: Simultaneous generalization of urban-scene segmentation to all adverse weather conditions [PDF] [G-Scholar]

• SaN [Bahmani et al., Proc. ECCV Workshops 2022] Semantic self-adaptation: Enhancing generalization with a single sample [PDF] [G-Scholar] [CODE]

• SR-TTT [Lyu et al., IEEE TMI 2022] Learning from synthetic CT images via test-time training for liver tumor segmentation [PDF] [G-Scholar] [CODE]

• Slot-TTA [Prabhudesai et al., Proc. ICML 2023] Test-time adaptation with slot-centric models [PDF] [G-Scholar] [CODE]

  [Prabhudesai et al., Proc. NeurIPS Workshops 2022] Test-time adaptation with slot-centric models [PDF] [G-Scholar]

• DIGA [Wang et al., Proc. CVPR 2023] Dynamically instance-guided adaptation: A backward-free approach for test-time domain adaptive semantic segmentation [PDF] [G-Scholar] [CODE]

• CMA [Bruggemann et al., Proc. ICCV 2023] Contrastive model adaptation for cross-condition robustness in semantic segmentation [PDF] [G-Scholar] [CODE]

• RNA [Dumpala et al., Proc. ICCV 2023] Rapid network adaptation: Learning to adapt neural networks using test-time feedback [PDF] [G-Scholar]

• Adaptive-UNet [Valanarasu et al., Proc. MIDL 2023] On-the-fly test-time adaptation for medical image segmentation [PDF] [G-Scholar] [CODE]

• WOSA-AugSelf [Huang et al., Computer Methods and Programs in Biomedicine 2023] Test-time bi-directional adaptation between image and model for robust segmentation [PDF] [G-Scholar]

• AdaAtlas [Guo et al., arXiv 2023] Pay attention to the atlas: Atlas-guided test-time adaptation method for robust 3D medical image segmentation [PDF] [G-Scholar]

• ... [Janouskova et al., arXiv 2023] Single image test-time adaptation for segmentation [PDF] [G-Scholar] [CODE--]

• DG-TTA [Weihsbach et al., arXiv 2023] DG-TTA: Out-of-domain medical image segmentation through domain generalization and test-time adaptation [PDF] [G-Scholar] [CODE--]

• TTA-SEG [Janouskova., Master Thesis 2023] Test-time adaptation for segmentation [PDF] [G-Scholar--] [CODE]

2024

• Decorruptor [Oh et al., Proc. ECCV 2024] Efficient diffusion-driven corruption editor for test-time adaptation [PDF] [G-Scholar] [CODE]

• GenSAM [Hu et al., Proc. AAAI 2024] Relax image-specific prompt requirement in SAM: A single generic prompt for segmenting camouflaged objects [PDF] [G-Scholar] [CODE]

• TTT4AS [Costanzino et al., Proc. CVPR Workshops 2024] Test time training for industrial anomaly segmentation [PDF] [G-Scholar]

• SaLIP [Aleem et al., Proc. CVPR Workshops 2024] Test-time adaptation with SaLIP: A cascade of SAM and CLIP for zero-shot medical image segmentation [PDF] [G-Scholar] [CODE]

• ... [Basak and Yin, Proc. MICCAI 2024] Quest for clone: Test-time domain adaptation for medical image segmentation by searching the closest clone in latent space [PDF] [G-Scholar--] [CODE--]

• ... [Gérin et al., Proc. CAI 2024] Exploring viability of test-time training: Application to 3D segmentation in multiple sclerosis [PDF] [G-Scholar] [CODE--]

• ... [Lee et al., IEEE TGRS 2024] Fine-grained binary segmentation for geospatial objects in remote sensing imagery via path-selective test-time adaptation [PDF] [G-Scholar--]

• Adaptive WaVNet [Qian et al., Medical Physics 2024] Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation [PDF] [G-Scholar]

• InTEnt [Dong et al., arXiv 2024] Medical image segmentation with InTEnt: Integrated entropy weighting for single image test-time adaptation [PDF] [G-Scholar] [CODE--]

• TTT-KD [Weijler et al., arXiv 2024] TTT-KD: Test-time training for 3D semantic segmentation through knowledge distillation from foundation models [PDF] [G-Scholar]

• ... [Zhang et al., arXiv 2024] Refining segmentation on-the-fly: An interactive framework for point cloud semantic segmentation [PDF] [G-Scholar]

• ... [Schön et al., arXiv 2024] Adapting the segment anything model during usage in novel situations [PDF] [G-Scholar]

• PASS [Zhang et al., arXiv 2024] PASS: Test-time prompting to adapt styles and semantic shapes in medical image segmentation [PDF] [G-Scholar--] [CODE]

• InvSeg [Lin et al., arXiv 2024] InvSeg: Test-time prompt inversion for semantic segmentation [PDF] [G-Scholar] [CODE--]

Detection

• OSHOT [D'Innocente et al., Proc. ECCV 2020] One-shot unsupervised cross-domain detection [PDF] [G-Scholar] [CODE]

• Full-OSHOT [Borlino et al., Computer Vision and Image Understanding 2022] Self-supervision & meta-learning for one-shot unsupervised cross-domain detection [PDF] [G-Scholar] [CODE]

• ... [Veksler., Proc. CVPR 2023] Test time adaptation with regularized loss for weakly supervised salient object detection [PDF] [G-Scholar]

• ... [Shen et al., Proc. ICASSP 2024] One-epoch training with single test sample in test time for better generalization of cough-based Covid-19 detection model [PDF] [G-Scholar--]

Attack and Defense

• SOAP [Shi et al., Proc. ICLR 2021] Online adversarial purification based on self-supervision [PDF] [G-Scholar] [CODE]

• ADP [Yoon et al., Proc. ICML 2021] Adversarial purification with score-based generative models [PDF] [G-Scholar] [CODE]

• SSRA [Mao et al., Proc. ICCV 2021] Adversarial attacks are reversible with natural supervision [PDF] [G-Scholar] [CODE]

• Hedge [Wu et al., arXiv 2021] Attacking adversarial attacks as a defense [PDF] [G-Scholar]

• Anti-Adv [Alfarra et al., Proc. AAAI 2022] Combating adversaries with anti-adversaries [PDF] [G-Scholar] [CODE]

• ReScaler [Gudibande et al., Proc. CVPR Workshops 2022] Test-time adaptation of residual blocks against poisoning and backdoor attacks [PDF] [G-Scholar--]

• Equ-Defense [Mao et al., arXiv 2022] Robust perception through equivariance [PDF] [G-Scholar]

• CVP [Tsai et al., Proc. NeurIPS 2023] Convolutional visual prompt for robust visual perception [PDF] [G-Scholar]

• Mask-Defense [McDermott et al., Proc. ICLR Workshops 2023] Robustifying language models with test-time adaptation [PDF] [G-Scholar--]

• DRAM [Tsai et al., arXiv 2023] Test-time defense against adversarial attacks: Detection and reconstruction of adversarial examples via masked autoencoder [PDF] [G-Scholar]

  [Tsai et al., Proc. CVPR Workshops 2023] Test-time detection and repair of adversarial samples via masked autoencoder [PDF] [G-Scholar--]

• TETRA [Blau et al., arXiv 2023] Classifier robustness enhancement via test-time transformation [PDF] [G-Scholar]

• ZIP [Shi et al., arXiv 2023] Black-box backdoor defense via zero-shot image purification [PDF] [G-Scholar]

• BDMAE [Sun et al., arXiv 2023] Mask and restore: Blind backdoor defense at test time with masked autoencoder [PDF] [G-Scholar]

• RFI [Singh et al., arXiv 2023] Fast adaptive test-time defense with robust features [PDF] [G-Scholar]

• MAT [Huang et al., Misc 2023] Test-time adaptation for better adversarial robustness [PDF] [G-Scholar--]

• MedBN [Park et al., Proc. CVPR 2024] MedBN: Robust test-time adaptation against malicious test samples [PDF] [G-Scholar] [CODE--]

• TPAP [Tang and Zhang, Proc. CVPR 2024] Robust overfitting does matter: Test-time adversarial purification with FGSM [PDF] [G-Scholar] [CODE]

• IG-Defense [Kulkarni and Weng, Proc. ECCV 2024] Interpretability-guided test-time adversarial defense [PDF] [G-Scholar] [CODE]

• TTD [Yang et al., Proc. AAAI 2024] Adversarial purification with the manifold hypothesis [PDF] [G-Scholar]

• ... [Shaikh et al., Proc. CVPR Workshops 2024] Adaptive randomized smoothing for certified multi-step defence [PDF] [G-Scholar--]

• ... [Yeh et al., arXiv 2024] Test-time adversarial defense with opposite adversarial path and high attack time cost [PDF] [G-Scholar--]

Pose estimation

• ISO [Zhang et al., Proc. NeurIPS 2020] Inference stage optimization for cross-scenario 3d human pose estimation [PDF] [G-Scholar]

• SCIO [Kan et al., Proc. ECCV 2022] Self-constrained inference optimization on structural groups for human pose estimation [PDF] [G-Scholar]

• ZPT [Wang et al., Proc. ECCV 2022] Zero-shot pose transfer for unrigged stylized 3D characters [PDF] [G-Scholar]

• ... [Azarian et al., Proc. WACV Workshops 2023] Test-time adaptation vs. training-time generalization: A case study in human instance segmentation using keypoints estimation [PDF] [G-Scholar]

• ... [Chen et al., IEEE TMM 2023] Multi-person 3D pose esitmation with occlusion reasoning [PDF] [G-Scholar]

• AB-TTA [Xu et al., Proc. CVPR 2024] Dexterous grasp transformer [PDF] [G-Scholar] [CODE--]

• ... [Pérez-Villar et al., IEEE TAES 2024] Test-time adaptation for keypoint-based spacecraft pose estimation based on predicted-view synthesis [PDF] [G-Scholar--] [CODE]

• UAO [Wang et al., arXiv 2024] Uncertainty-aware testing-time optimization for 3D human pose estimation [PDF] [G-Scholar]

Retrieval

• Sketch3T [Sain et al., Proc. CVPR 2022] Sketch3t: Test-time training for zero-shot SBIR [PDF] [G-Scholar]

• TTT-UCDR [Paul et al., arXiv 2022] TTT-UCDR: Test-time training for universal cross-domain retrieval [PDF] [G-Scholar] [CODE]

• META [Xu et al., Proc. ECCV 2022] Mimic embedding via adaptive aggregation: Learning generalizable person re-identification [PDF] [G-Scholar] [CODE]

Low-level vision

• ZSSR [Shocher et al., Proc. CVPR 2018] "zero-shot" super-resolution using deep internal learning [PDF] [G-Scholar] [CODE]

• MLSR [Park et al., Proc. ECCV 2020] Fast adaptation to super-resolution networks via meta-learning [PDF] [G-Scholar] [CODE]

• MZSR [Soh et al., Proc. CVPR 2020] Meta-transfer learning for zero-shot super-resolution [PDF] [G-Scholar] [CODE]

• LIDIA [Vaksman et al., Proc. CVPR Workshops 2020] Lidia: Lightweight learned image denoising with instance adaptation [PDF] [G-Scholar] [CODE]

• SURE-FT [Soltanayev and Chun, arXiv 2021] Training deep learning based denoisers without ground truth data [PDF] [G-Scholar] [CODE]

• Gaintuning [Mohan et al., Proc. NeurIPS 2021] Adaptive denoising via gaintuning [PDF] [G-Scholar] [CODE--]

• MetaAT [Chi et al., Proc. CVPR 2021] Test-time fast adaptation for dynamic scene deblurring via meta-auxiliary learning [PDF] [G-Scholar]

• ... [Liu et al., Proc. CVPR 2022] Towards multi-domain single image dehazing via test-time training [PDF] [G-Scholar]

• MetaTL [Gunawan et al., arXiv 2022] Test-time adaptation for real image denoising via meta-transfer learning [PDF] [G-Scholar] [CODE]

• SRTTA [Deng et al., Proc. NeurIPS 2023] Efficient test-time adaptation for super-resolution with second-order degradation and reconstruction [PDF] [G-Scholar] [CODE--]

• ... [Hatem et al., Proc. IROS 2023] Test-time adaptation for point cloud upsampling using meta-learning [PDF] [G-Scholar]

• PTTD [Chen et al., arXiv 2023] Prompt-based test-time real image dehazing: A novel pipeline [PDF] [G-Scholar] [CODE]

• TAO [Gou et al., Proc. ICML 2024] Test-time degradation adaptation for open-set image restoration [PDF] [G-Scholar--] [CODE--]

• LAN [Kim et al., Proc. CVPR 2024] LAN: Learning to adapt noise for image denoising [PDF] [G-Scholar--]

• UTAL [Zhang et al., IEEE TPAMI 2024] Unsupervised test-time adaptation learning for effective hyperspectral image super-resolution with unknown degeneration [PDF] [G-Scholar]

• ... [Li et al., IEEE TPAMI 2024] Test-time training for hyperspectral image super-resolution [PDF] [G-Scholar]

Inverse problem

• R&R+ [Gilton et al., IEEE TCI 2021] Model adaptation for inverse problems in imaging [PDF] [G-Scholar]

• IAGAN-BP [Hussein et al., Proc. AAAI 2020] Image-adaptive GAN based reconstruction [PDF] [G-Scholar] [CODE]

• ... [Darestani et al., Proc. ICML 2022] Test-time training can close the natural distribution shift performance gap in deep learning based compressed sensing [PDF] [G-Scholar] [CODE]

• PINER [Song et al., Proc. WACV 2023] PINER: Prior-informed implicit neural representation learning for test-time adaptation in sparse-view CT reconstruction [PDF] [G-Scholar]

• PnP-TTT [Chandler et al., Proc. CAMSAP 2023] Overcoming distribution shifts in plug-and-play methods with test-time training [PDF] [G-Scholar--]

• DIP-Inv [Xu and Heagy, arXiv 2023] A test-time learning approach to reparameterize the geophysical inverse problem with a convolutional neural network [PDF] [G-Scholar]

• OML [Wang et al., IEEE Transactions on Radiation and Plasma Medical Sciences 2024] Test-time adaptation via orthogonal meta-learning for medical imaging [PDF] [G-Scholar--]

• ... [Klug et al., arXiv 2024] MotionTTT: 2D test-time-training motion estimation for 3D motion corrected MRI [PDF] [G-Scholar]

Mapping between paired images

• SSMSR [Zhu et al., Proc. ICRA 2021] Test-time training for deformable multi-scale image registration [PDF] [G-Scholar]

• ... [Baum et al., Proc. MICCAI Workshops 2022] Meta-registration: Learning test-time optimization for single-pair image registration [PDF] [G-Scholar]

• DMP [Hong and Kim, Proc. ICCV 2021] Deep matching prior: Test-time optimization for dense correspondence [PDF] [G-Scholar] [CODE--]

• ... [Hatem et al., Proc. ICCV 2023] Point-TTA: Test-time adaptation for point cloud registration using multitask meta-auxiliary learning [PDF] [G-Scholar]

• MLOF [Min et al., Proc. WACV 2023] Meta-learning for adaptation of deep optical flow networks [PDF] [G-Scholar] [CODE]

• ... [Sang et al., Medical Physics 2023] Target‐oriented deep learning‐based image registration with individualized test‐time adaptation [PDF] [G-Scholar]

• ... [Tirer et al., arXiv 2023] Deep internal learning: Deep learning from a single input [PDF] [G-Scholar]

• SGTTA [Zhou et al., Proc. AAAI 2024] Test-time adaptation via style and structure guidance for histological image registration [PDF] [G-Scholar--]

• MeTTA [Kim et al., Proc. BMVC 2024] MeTTA: Single-view to 3D textured mesh reconstruction with test-time adaptation [PDF] [G-Scholar--]

Generative modeling

• GIP [Bau et al., ACM TOG 2019] Semantic photo manipulation with a generative image prior [PDF] [G-Scholar]

• INR-st [Kim et al., arXiv 2022] Controllable style transfer via test-time training of implicit neural representation [PDF] [G-Scholar] [CODE]

• SiSTA [Subramanyam et al., Proc. ICML 2023] Target-aware generative augmentations for single-shot adaptation [PDF] [G-Scholar] [CODE]

  [Subramanyam et al., arXiv 2022] Single-shot domain adaptation via target-aware generative augmentation [PDF] [G-Scholar]

• MODIFY [Ding et al., Proc. ICASSP 2023] MODIFY: Model-driven face stylization without style images [PDF] [G-Scholar]

Consistency

• SSL-MOCAP [Tung et al., Proc. NeurIPS 2017] Self-supervised learning of motion capture [PDF] [G-Scholar] [CODE]

• MetaVFI [Choi et al., Proc. CVPR 2020] Scene-adaptive video frame interpolation via meta-learning [PDF] [G-Scholar]

• REFINE [Leung et al., Proc. CVPR Workshops 2022] Black-box test-time shape REFINEment for single view 3D reconstruction [PDF] [G-Scholar] [CODE]

• MetaVFI [Choi et al., IEEE TPAMI 2021] Test-time adaptation for video frame interpolation via meta-learning [PDF] [G-Scholar]

• VFI_Adapter [Wu et al., arXiv 2023] Boost video frame interpolation via motion adaptation [PDF] [G-Scholar] [CODE]

• TTA-EVF [Cho et al., Proc. CVPR 2024] TTA-EVF: Test-time adaptation for event-based video frame interpolation via reliable pixel and sample estimation [PDF] [G-Scholar] [CODE]

• DADeblur [He et al., Proc. ECCV 2024] Domain-adaptive video deblurring via test-time blurring [PDF] [G-Scholar] [CODE--]

• DINO-Tracker [Tumanyan et al., arXiv 2024] DINO-Tracker: Taming DINO for self-supervised point tracking in a single video [PDF] [G-Scholar] [CODE]

• VIA [Gu et al., arXiv 2024] VIA: A spatiotemporal video adaptation framework for global and local video editing [PDF] [G-Scholar--] [CODE--]

Action Recognition

• T3AL [Liberatori et al., Proc. CVPR 2024] From denoising training to test-time adaptation: Enhancing domain generalization for medical image segmentation [PDF] [G-Scholar] [CODE]

NLP

• TTL-EQA [Banerjee et al., Proc. NAACL 2021] Self-supervised test-time learning for reading comprehension [PDF] [G-Scholar]

• EMEA [Wang et al., Proc. EMNLP-Findings 2021] Efficient test time adapter ensembling for low-resource language varieties [PDF] [G-Scholar]

• PADA [Ben-David et al., TACL 2022] PADA: Example-based prompt learning for on-the-fly adaptation to unseen domains [PDF] [G-Scholar] [CODE]

• Hyper-PADA [Volk et al., arXiv 2022] Example-based hypernetworks for out-of-distribution generalization [PDF] [G-Scholar] [CODE]

• T-SAS [Jeong et al., Proc. EMNLP-Findings 2023] Test-time self-adaptive small languagem models for question answering [PDF] [G-Scholar--] [CODE--]

• AGREE [Ye et al., arXiv 2023] Effective large language model adaptation for improved grounding [PDF] [G-Scholar]

• TTT-NN [Hardt and Sun, Proc. ICLR 2024] Test-time training on nearest neighbors for large language models [PDF] [G-Scholar] [CODE]

• TTTLayers [Sun et al., arXiv 2024] Learning to (learn at test time): RNNs with expressive hidden states [PDF] [G-Scholar] [CODE]

• iP-VAE [Vafaii et al., arXiv 2024] A prescriptive theory for brain-like inference [PDF] [G-Scholar]

• ... [Akyürek et al., Misc 2024] The surprising effectiveness of test-time training for abstract reasoning [PDF] [G-Scholar--]

Graph

• GT3 [Wang et al., arXiv 2022] Test-time training for graph neural networks [PDF] [G-Scholar]

• GTRANS [Jin et al., Proc. ICLR 2023] Empowering graph representation learning with test-time graph transformation [PDF] [G-Scholar]

• T3RD [Zhang et al., Proc. WWW 2024] T3RD: Test-time training for rumor detection on social media [PDF] [G-Scholar--] [CODE]

• ... [Chen et al., Proc. SDM 2024] Test-time training for spatial-temporal forecasting [PDF] [G-Scholar--]

• GOODAT [Wang et al., arXiv 2024] GOODAT: Towards test-time graph out-of-distribution detection [PDF] [G-Scholar]

• TARD [Tao et al., arXiv 2024] Out-of-distribution rumor detection via test-time adaptation [PDF] [G-Scholar]

• ProteinTTT [Bushuiev et al., arXiv 2024] Training on test proteins improves fitness, structure, and function prediction [PDF] [G-Scholar] [CODE]

CLIP-related

• TPT [Shu et al., Proc. NeurIPS 2022] Test-time prompt tuning for zero-shot generalization in vision-language models [PDF] [G-Scholar] [CODE]

• DiffTPT [Feng et al., Proc. ICCV 2023] Diverse data augmentation with diffusions for effective test-time prompt tuning [PDF] [G-Scholar] [CODE--]

• AutoCLIP [Metzen et al., arXiv 2023] AutoCLIP: Auto-tuning zero-shot classifiers for vision-language models [PDF] [G-Scholar]

• RLCF [Zhao et al., Proc. ICLR 2024] Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models [PDF] [G-Scholar] [CODE]

• C-TPT [Yoon et al., Proc. ICLR 2024] C-TPT: Calibrated test-time prompt tuning for vision-language models via text feature dispersion [PDF] [G-Scholar]

• APM [Modi and Rawat, Proc. NeurIPS 2024] Asynchronous perception machine for Efficient test time training [PDF] [G-Scholar] [CODE--]

• MTA [Zanella and Ayed, Proc. CVPR 2024] On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning? [PDF] [G-Scholar] [CODE]

• SCP [Wang et al., Proc. ACM MM 2024] Towards robustness prompt tuning with fully test-time adaptation for CLIP’s zero-shot generalization [PDF] [G-Scholar--]

• PromptSync [Khandelwal, Proc. CVPR Workshops 2024] PromptSync: Bridging domain gaps in vision-language models through class-aware prototype alignment and discrimination [PDF] [G-Scholar]

• TT-DNA [Zhang and Zhang, Proc. ICASSP 2024] Test-time distribution learning adapter for cross-modal visual reasoning [PDF] [G-Scholar]

• InTTA [Ma et al., arXiv 2024] Invariant test-time adaptation for vision-language model generalization [PDF] [G-Scholar--] [CODE]

• TPS [Sui et al., arXiv 2024] Just shift it: Test-time prototype shifting for zero-shot generalization with vision-language models [PDF] [G-Scholar] [CODE]

• InCPL [Yin et al., arXiv 2024] In-context prompt learning for test-time vision recognition with frozen vision-language model [PDF] [G-Scholar]

• Domain++ CLIP-T [Hou et al., arXiv 2024] DomainVerse: A benchmark towards real-world distribution shifts for tuning-free adaptive domain generalization [PDF] [G-Scholar]

• WATT [Osowiechi et al., arXiv 2024] WATT: Weight average test-time adaptation of CLIP [PDF] [G-Scholar--] [CODE]

• CPT [Zhu et al., arXiv 2024] Efficient test-time prompt tuning for vision-language models [PDF] [G-Scholar]

• TTL [Imam et al., arXiv 2024] Test-time low rank adaptation via confidence maximization for zero-shot generalization of vision-language models [PDF] [G-Scholar] [CODE]

• ... [Zhang et al., arXiv 2024] StylePrompter: Enhancing domain generalization with test-time style priors [PDF] [G-Scholar--]

Audio Classification

• ... [Chen et al., Misc 2024] Acoustic scene classification by the self-learning of eat [PDF] [G-Scholar--]

• ... [Huang et al., Misc 2024] Semi-supervised acoustic scene classification with test-time adaptation [PDF] [G-Scholar--]

Face

• GPR [Jain and Learned-Miller, Proc. CVPR 2011] Online domain adaptation of a pre-trained cascade of classifiers [PDF] [G-Scholar]

• TTSP [Zhou et al., Proc. CVPR 2024] Test-time domain generalization for face anti-spoofing [PDF] [G-Scholar]

• ELF-UA [Wu et al., Proc. IJCAI 2024] ELF-UA: Efficient label-free user adaptation in gaze estimation [PDF] [G-Scholar]

Gaze estimation

• TPGaze [Liu et al., Proc. AAAI 2024] Test-time personalization with meta prompt for gaze estimation [PDF] [G-Scholar--]

Image manipulation localization

• ForgeryTTT [Liu et al., arXiv 2024] ForgeryTTT: Zero-shot image manipulation localization with test-time training [PDF] [G-Scholar--]

Misc

• PAD [Hansen et al., Proc. ICLR 2021] Self-supervised policy adaptation during deployment [PDF] [G-Scholar] [CODE]

• RoMA [Yu et al., Proc. NeurIPS 2021] RoMA: Robust model adaptation for offline model-based optimization [PDF] [G-Scholar] [CODE]

• ZSDA-HTL [Sakai, Proc. ECML-PKDD 2021] Source hypothesis transfer for zero-shot domain adaptation [PDF] [G-Scholar]

• VoP [Kim et al., Proc. ICML 2022] Variational on-the-fly personalization [PDF] [G-Scholar]

• OST [Chen et al., Proc. NeurIPS 2022] OST: Improving generalization of DeepFake detection via one-shot test-time training [PDF] [G-Scholar] [CODE]

• ... [Özer and Müller, Proc. ISMIR 2022] Source separation of piano concertos with test-time adaptation [PDF] [G-Scholar]

• ... [Sang et al., International Journal of Radiation Oncology, Biology, Physics 2022] Inference-time adaptation for improved transfer ability and generalization in deformable image registration deep learning [PDF] [G-Scholar]

• DFA [Mirza et al., Proc. ICML 2023] Diagnosis, feedback, adaptation: A human-in-the-loop framework for test-time policy adaptation [PDF] [G-Scholar]

• DROP [Liu et al., Proc. NeurIPS 2023] Design from policies: Conservative test-time adaptation for offline policy optimization [PDF] [G-Scholar]

• PAFF [Ge et al., Proc. CVPR 2023] Policy adaptation from foundation model feedback [PDF] [G-Scholar]

• MATE [Mirza et al., Proc. ICCV 2023] MATE: Masked autoencoders are online 3D test-time learners [PDF] [G-Scholar] [CODE]

• ... [Liu et al., Proc. WACV 2023] Meta-auxiliary learning for future depth prediction in videos [PDF] [G-Scholar]

• ... [Zheng et al., Proc. PRCV 2023] Infrared and visible image fusion via test-time training [PDF] [G-Scholar]

• TDS [Wen et al., IEEE TMM 2023] Test-time model adaptation for visual question answering with debiased self-supervisions [PDF] [G-Scholar]

• PepT3 [Ye et al., Journal of Proteome Research 2023] Test-time training for deep MS/MS spectrum prediction improves peptide identification [PDF] [G-Scholar] [CODE]

• SRR-MAML [Huo et al., arXiv 2023] Learning adaptable risk-sensitive policies to coordinate in multi-agent general-sum games [PDF] [G-Scholar]

• ARSP [Liu and Fang, arXiv 2023] Learning to recover spectral reflectance from RGB images [PDF] [G-Scholar]

• MoVie [Yang et al., arXiv 2023] MoVie: Visual model-based policy adaptation for view generalization [PDF] [G-Scholar] [CODE]

• ... [Dumpala et al., arXiv 2023] Test-time training for speech [PDF] [G-Scholar]

• TPC [Yoon et al., Proc. NeurIPS 2024] TPC: Test-time procrustes calibration for diffusion-based human image animation [PDF] [G-Scholar--]

• ... [Zhou et al., Proc. ECML-PKDD 2024] Contrastive learning enhanced diffusion model for improving tropical cyclone intensity estimation with test-time adaptation [PDF] [G-Scholar] [CODE]

• TICA [Zhu et al., Proc. ICONIP 2024] Test-time intensity consistency adaptation for shadow detection [PDF] [G-Scholar]

• ... [Schopf-Kuester et al., Proc. ICML Workshops 2024] 3D shape completion with test-time training [PDF] [G-Scholar--] [CODE--]

• DTDA [Zhang et al., IEEE TMI 2024] Constraint-aware learning for fractional flow reserve pullback curve estimation from invasive coronary imaging [PDF] [G-Scholar]

• ... [Deshmukh et al., arXiv 2024] Domain adaptation for contrastive audio-language models [PDF] [G-Scholar]

• TTA-Nav [Piriyajitakonkij et al., arXiv 2024] TTA-Nav: Test-time adaptive reconstruction for point-goal navigation under visual corruptions [PDF] [G-Scholar]

• GTTA-ST [Feng et al., arXiv 2024] GPT4Battery: An LLM-driven framework for adaptive state of health estimation of raw Li-ion batteries [PDF] [G-Scholar]

• AudioMAE-TTT [Dumpala et al., arXiv 2024] Test-time training for depression detection [PDF] [G-Scholar--]

• ... [Yu et al., arXiv 2024] DPA-Net: Structured 3D abstraction from sparse views via differentiable primitive assembly [PDF] [G-Scholar]

• ... [Wu et al., arXiv 2024] Efficient domain adaptation for endoscopic visual odometry [PDF] [G-Scholar]

Batch-level

Classification

• ARM [Zhang et al., Proc. NeurIPS 2021] Adaptive risk minimization: Learning to adapt to domain shift [PDF] [G-Scholar] [CODE]

• DA-ERM [Dubey et al., Proc. CVPR 2021] Adaptive methods for real-world domain generalization [PDF] [G-Scholar] [CODE]

• ... [Benz et al., Proc. WACV 2021] Revisiting batch normalization for improving corruption robustness [PDF] [G-Scholar] [CODE]

• ... [Nandy et al., Proc. ICLR Workshops 2021] Covariate shift adaptation for adversarially robust classifier [PDF] [G-Scholar]

• Meta-DMoE [Zhong et al., Proc. NeurIPS 2022] Meta-DMoE: Adapting to domain shift by meta-distillation from mixture-of-experts [PDF] [G-Scholar] [CODE]

• TTAwPCA [Cordier et al., Proc. ECML/PKDD Workshops 2022] Test-time adaptation with principal component analysis [PDF] [G-Scholar]

• L2GP [Duboudin et al., arXiv 2022] Learning less generalizable patterns with an asymmetrically trained double classifier for better test-time adaptation [PDF] [G-Scholar]

2023

• ShiftMatch [Wang and Aitchison, Proc. ICLR 2023] Robustness to corruption in pre-trained Bayesian neural networks [PDF] [G-Scholar]

• DN [Zhou et al., Proc. NeuIPS 2023] Test-time distribution normalization for contrastively learned vision-language models [PDF] [G-Scholar] [CODE]

• ATP [Bao et al., Proc. NeuIPS 2023] Adaptive test-time personalization for federated learning [PDF] [G-Scholar] [CODE--]

• DomainAdaptor [Zhang et al., Proc. ICCV 2023] DomainAdaptor: A novel approach to test-time adaptation [PDF] [G-Scholar] [CODE]

• ClusT3 [Hakim et al., Proc. ICCV 2023] ClusT3: Information invariant test-time training [PDF] [G-Scholar] [CODE--]

• TTTFlow [Osowiechi et al., Proc. WACV 2023] TTTFlow: Unsupervised test-time training with normalizing flow [PDF] [G-Scholar] [CODE]

• TTN [Vianna et al., Proc. NeuIPS Workshops 2023] Channel selection for test-time adaptation under distribution shift [PDF] [G-Scholar--]

• DILAM [Leitner et al., Proc. IEEE Intelligent Vehciles Symposium 2023] Sit back and relax: Learning to drive incrementally in all weather conditions [PDF] [G-Scholar] [CODE]

• CVP [Tsai et al., arXiv 2023] Self-supervised convolutional visual prompts [PDF] [G-Scholar]

• ContextViT [Bao and Karaletsos, arXiv 2023] Contextual vision transformers for robust representation learning [PDF] [G-Scholar]

• ... [Rezaei and Norouzzadeh, arXiv 2023] Dynamic batch norm statistics update for natural robustness [PDF] [G-Scholar--]

• ... [Müller et al., arXiv 2023] Towards context-aware domain generalization: Representing environments with permutation-invariant networks [PDF] [G-Scholar]

2024

• NC-TTT [Osowiechi et al., Proc. CVPR 2024] NC-TTT: A noise contrastive approach for test-time training [PDF] [G-Scholar] [CODE]

• MABN [Wu et al., Proc. AAAI 2024] Test-time domain adaptation by learning domain-aware batch normalization [PDF] [G-Scholar] [CODE]

• ... [Haslum et al, Proc. WACV 2024] Bridging generalization gaps in high content imaging through online self-supervised domain adaptation [PDF] [G-Scholar]

• ... [Amosy et al., Proc. WACV 2024] Late to the party? On-demand unlabeled personalized federated learning [PDF] [G-Scholar]

• ABNN [Lo and Patel, Proc. AVSS 2024] Adaptive batch normalization networks for adversarial robustness [PDF] [G-Scholar]

• Hybrid-TTN [Vianna et al, arXiv 2024] Channel-selective normalization for label-shift robust test-time adaptation [PDF] [G-Scholar]

• PAN [Camuffo et al., arXiv 2024] Enhanced model robustness to input corruptions by per-corruption adaptation of normalization statistics [PDF] [G-Scholar]

Video processing (multiple frames)

• PGO [Brahmbhatt et al., Proc. CVPR 2018] Geometry-aware learning of maps for camera localization [PDF] [G-Scholar] [CODE]

• Struct2depth [Casser et al., Proc. AAAI 2019] Depth prediction without the sensors: Leveraging structure for unsupervised learning from monocular videos [PDF] [G-Scholar] [CODE]

• GLNet [Chen et al., Proc. ICCV 2019] Self-supervised learning with geometric constraints in monocular video: Connecting flow, depth, and camera [PDF] [G-Scholar]

• ACMR-vid [Li et al., Proc. NeurIPS 2020] Online adaptation for consistent mesh reconstruction in the wild [PDF] [G-Scholar]

• CVD [Luo et al., ACM TOG 2020] Consistent video depth estimation [PDF] [G-Scholar] [CODE]

• Deep3D [Lee et al., Proc. CVPR 2021] 3D video stabilization with depth estimation by CNN-based optimization [PDF] [G-Scholar]

• GCVD [Lee et al., arXiv 2022] Globally consistent video depth and pose estimation with efficient test-time training [PDF] [G-Scholar] [CODE]

• ... [Azimi et al., Proc. WACV 2022] Self-supervised test-time adaptation on video data [PDF] [G-Scholar]

• ... [Yeh et al., Proc. CVPR 2023] Meta-personalizing vision-language models to find named instances in video [PDF] [G-Scholar]

• CycleAdapt [Nam et al., Proc. ICCV 2023] Cyclic test-time adaptation on monocular video for 3D human mesh reconstruction [PDF] [G-Scholar] [CODE]

• ... [Mutlu et al., arXiv 2023] TempT: Temporal consistency for test-time adaptation [PDF] [G-Scholar]

• Meta-VPL [Ambekar et al., arXiv 2023] Learning variational neighbor labels for test-time domain generalization [PDF] [G-Scholar]

• ... [Liu et al., arXiv 2023] Advancing test-time adaptation for acoustic foundation models in open-world shifts [PDF] [G-Scholar]

• ... [Liu et al., Proc. CVPR 2024] Depth-aware test-time training for zero-shot video object segmentation [PDF] [G-Scholar] [CODE]

• ... [Ali et al., Proc. CVPR 2024] Harnessing meta-learning for improving full-frame video stabilization [PDF] [G-Scholar] [CODE--]

• DTS-TPT [Yan et al, Proc. IJCAI 2024] DTS-TPT: Dual temporal-sync test-time prompt Tuning for zero-shot activity recognition [PDF [G-Scholar--]

• BISSA [Yoo et al., Pattern Recognition 2024] Looking beyond input frames: Self-supervised adaptation for video super-resolution [PDF] [G-Scholar] [CODE]

• ... [Wu et al., arXiv 2024] DeNVeR: Deformable neural vessel representations for unsupervised video vessel segmentation [PDF] [G-Scholar]

Misc

• TTP [Li et al., Proc. NeurIPS 2021] Test-time personalization with a transformer for human pose estimation [PDF] [G-Scholar] [CODE]

• BNTA [Han et al., Proc. AAAI 2022] Generalizable person re-identification via self-supervised batch norm test-time adaption [PDF] [G-Scholar]

• TTAS [Bateson et al., Proc. MICCAI 2022] Test-time adaptation with shape moments for image segmentation [PDF] [G-Scholar] [CODE]

• SUTA [Lin et al., Proc. Interspeech 2022] Listen, adapt, better WER: Source-free single-utterance test-time adaptation for automatic speech recognition [PDF] [G-Scholar] [CODE]

• MyStyle [Nitzan et al., ACM TOG 2022] MyStyle: A personalized generative prior [PDF] [G-Scholar] [CODE]

• MetaSSN [Kim et al., Expert Systems with Applications 2022] Style selective normalization with meta learning for test-time adaptive face anti-spoofing [PDF] [G-Scholar]

• LSTM [Benmalek et al., Misc 2022] Learning to adapt to semantic shift [PDF] [G-Scholar--]

2023

• DIA [Wu et al., Proc. ICML 2023] Uncovering adversarial risks of test-time adaptation [PDF] [G-Scholar]

• SCIA [Kan et al., Proc. CVPR 2023] Self-correctable and adaptable inference for generalizable human pose estimation [PDF] [G-Scholar]

• ... [Cui et al., Proc. ICCV 2023] Test-time personalizable forecasting of 3D human poses [PDF] [G-Scholar--]

• TTA-IQA [Roy et al., Proc. ICCV 2023] Test time adaptation for blind image quality assessment [PDF] [G-Scholar] [CODE--]

• ... [Cui et al., Proc. AAAI 2023] Meta-auxiliary learning for adaptive human pose prediction [PDF] [G-Scholar]

• ... [Yi and Kim, Proc. ICRA 2023] Test-time synthetic-to-real adaptive depth estimation [PDF] [G-Scholar--]

• LD-BN-ADAPT [Bhardwaj et al., Proc. DATE 2023] Real-time fully unsupervised domain adaptation for lane detection in autonomous driving [PDF] [G-Scholar--]

• SGEM [Kim et al., Proc. Interspeech 2023] SGEM: Test-time adaptation for automatic speech recognition via sequential-level generalized entropy minimization [PDF] [G-Scholar] [CODE]

• TTS [Bissoto et al., Proc. MICCAI Workshops 2023] Test-time selection for robust skin lesion analysis [PDF] [G-Scholar]

• MixTBN [Liu and Li, Proc. ICCASIT 2023] MixTBN: A fully test-time adaptation method for visual reinforcement learning on robotic manipulation [PDF] [G-Scholar--]

• ... [Mehra et al., arXiv 2023] On the fly neural style smoothing for risk-averse domain generalization [PDF] [G-Scholar]

• ... [Tula et al., arXiv 2023] Is it an i or an l: Test-time adaptation of text line recognition models [PDF] [G-Scholar]

2024

• ... [Cao et al., Proc. CVPR 2024] Spectral meets spatial: Harmonising 3D shape matching and interpolation [PDF] [G-Scholar]

• MeTTA [Hu et al., Proc. CVPR 2024] Fast adaptation for human pose estimation via meta-optimization [PDF] [G-Scholar--]

• LI-TTA [Yoon et al., Proc. Interspeech 2024] LI-TTA: Language informed test-time adaptation for automatic speech recognition [PDF] [G-Scholar] [CODE--]

• PAOA+ [Li and Gong, Proc. WACV 2024] Mitigate domain shift by primary-auxiliary objectives association for generalizing person ReID [PDF] [G-Scholar]

• ... [Wen et al., Proc. WACV 2024] From denoising training to test-time adaptation: Enhancing domain generalization for medical image segmentation [PDF] [G-Scholar]

• TTAGaze [Wu et al., IEEE TCSVT 2024] TTAGaze: Self-supervised test-time adaptation for personalized gaze estimation [PDF] [G-Scholar--]

• ICL-State-Vector [Li et al., arXiv 2024] In-context learning state vector with inner and momentum optimization [PDF] [G-Scholar] [CODE]

• DEnEM [Gilany et al., arXiv 2024] Calibrated diverse ensemble entropy minimization for robust test-time adaptation in prostate cancer detection [PDF] [G-Scholar]

• Adapted-MoE [Lei et al., arXiv 2024] Adapted-MoE: Mixture of experts with test-time adaption for anomaly detection [PDF] [G-Scholar--]

• ... [Shi et al., arXiv 2024] Personalized speech recognition for children with test-time adaptation [PDF] [G-Scholar--]

• TTT-Unet [Zhou et al., arXiv 2024] TTT-Unet: Enhancing U-Net with test-time training layers for biomedical image segmentation [PDF] [G-Scholar]